declaratie-prepare

declaratie-prepare is a skill for Claude Code from robert-malai/anafpy. It costs 139 tokens per session (2,328 once invoked), scanned A, original, Apache-2.0.

A workflow for preparing and filing Romanian tax declarations with ANAF, Romania’s tax authority, from source material such as emails, spreadsheets, or pasted figures.

In plain words
What is it for?
Use it to identify the correct Romanian tax form, create and validate its XML file, render it for review, and support signing and filing.
Why use it?
It reduces manual work while requiring every amount and choice to come from the source, a public lookup, or the user, and checks the declaration before filing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the anafpy-workflows plugin — 3 skills shipped together

Good fit Use it to identify the correct Romanian tax form, create and validate its XML file, render it for review, and support signing and filing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/robert-malai/anafpy/declaratie-prepare
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add robert-malai/anafpy --skill declaratie-prepare
Clone the repo
git clone --depth 1 https://github.com/robert-malai/anafpy

Made for: Claude Code.

Or install anafpy-workflows, the plugin that ships this one along with the rest of its 3 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for declaratie-prepare

README.md
[![agentmods](https://agentmods.dev/badge/skills/robert-malai/anafpy/declaratie-prepare/github.svg)](https://agentmods.dev/skills/robert-malai/anafpy/declaratie-prepare)
Your own site
<a href="https://agentmods.dev/skills/robert-malai/anafpy/declaratie-prepare"><img src="https://agentmods.dev/badge/skills/robert-malai/anafpy/declaratie-prepare/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for declaratie-prepare

Your own site · 80×15
<a href="https://agentmods.dev/skills/robert-malai/anafpy/declaratie-prepare"><img src="https://agentmods.dev/badge/skills/robert-malai/anafpy/declaratie-prepare.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00139 $0.02328
Opus 5 $0.00069 $0.01164
Sonnet 5 $0.00028 $0.00466
Haiku 4.5 $0.00014 $0.00233

Measured 9d ago against content hash 484ad9928dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

declaratie-prepare scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/anafpy-workflows/skills/declaratie-prepare/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build and file a tax declaration from source data

You are preparing a legal tax declaration for Romania's tax authority (ANAF) from whatever the user gives you — raw numbers, a document, or just a request. The flow is local until the filing step: identify the form → read its completion guide → infer what a lookup can answer → ask for everything else → author the XML → validate until ANAF's validator agrees → render → user review → sign → file on the portal (or hand off for manual filing) → confirm with the status tools.

Three rules override everything else:

  • Never invent a value. Every amount, period, and election must trace to the source data, a lookup result, or the user's answer. When something is missing, ask — do not guess. ANAF's validator, not you, is the authority.
  • Infer before you ask, ask before you assume. Identification data (company name, address, VAT status) comes from the CUI lookup, never from memory and never by asking the user to retype what ANAF publishes. Elections and amounts (settlement period, refund request, bank account, the numbers themselves) can never be inferred — always ask.
  • Never self-approve the signature — or the filing. declaratie_sign and declaratie_portal_login fire the user's certificate PIN/2FA, and declaratie_submit files a real declaration on the production portal (declarations have no test environment). Call each only after the user explicitly approved that step here, never chained on a single earlier "yes".

Step 1 — identify the form, orient the tooling

If the user already named the form (or it is unambiguous from their request), do not ask again — state which form you are preparing ("Working on D300, the VAT return for 06/2026") and move on. Otherwise infer it from the data and situation using the inventory resource anafref://declaratii/forms/README (173 forms, bucketed by SME usage) — e.g. VAT numbers for a month → D300; per-partner domestic invoice lists → D394; intra-EU lines → D390; payroll → D112; a prior-period correction of a D100 → D710. Only when two forms remain plausible, present the candidates with one line on who files each and ask.

Read the full file on GitHub · 177 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 177 lines · 139 tokens per session scan A 484ad9928dc6

Subscribe to this mod's changes

declaratie-prepare is a skill published in the GitHub repository robert-malai/anafpy (27 stars, last pushed 8d ago), licensed Apache-2.0. It adds 139 tokens to every session and 2,328 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

audit-support

Support SOX 404 compliance with control testing methodology, sample selection, and documentation standards. Use when generating testing workpapers, selecting audit samples, classifying control deficiencies, or preparing for internal or external audits.

anthropics/knowledge-work-plugins · 45 tokens

kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

anthropics/financial-services · 49 tokens

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

regulatory-analysis

Analyzes documents and processes against FINRA, SEC, Federal Reserve, and CFPB regulatory frameworks. Identifies compliance gaps, classifies findings by severity, and recommends remediation. Use when performing compliance audits, regulatory reviews, gap analyses, or verifying policy adherence to financial regulations.

open-gitagent/opengap · 59 tokens

subcontractor-payment-tracker

Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 25 tokens

tax-optimizer

Tax optimization strategies including tax-loss harvesting, wash sale rule navigation, asset location optimization, Roth conversion analysis, and charitable giving strategies.

CoWork-OS/CoWork-OS · 30 tokens